Real-time face tracking with GPU Acceleration
Fast and robust tracking of multiple faces is receiving increased attention from computer vision researchers as it finds potential applications in many fields like video surveillance and computer mediated video conferencing. Real-time tracking of multiple faces in high resolution videos involve three basic tasks namely initialization, tracking and display. Among these, tracking is quite compute intensive as it involves particle filtering that won't yield a real time performance if we use a conventional CPU based system alone. While looking forward a design that optimizes the system for an appreciable real-time performance, calls for the use of compute efficient platforms like GPU for compute intensive tasks along with conventional CPU. This paper discusses our heterogeneous design model which combines conventional programming for CPU efficient tasks and the nVIDIA CUDA for GP-GPU that implements the compute intensive tasks.
Keywords: Stream processing, GPU, GPGPU, CUDA, Particle filtering, video tracking, real-time systems.